Commit
•
ddcda86
1
Parent(s):
5c8d5da
End of training
Browse files- all_results.json +11 -0
- eval_results.json +6 -0
- train_results.json +8 -0
- trainer_state.json +301 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 88.31598864711448,
|
| 4 |
+
"eval_f1": 94.44474801701165,
|
| 5 |
+
"eval_samples": 10808,
|
| 6 |
+
"train_loss": 0.6275850592107118,
|
| 7 |
+
"train_runtime": 29795.4441,
|
| 8 |
+
"train_samples": 88638,
|
| 9 |
+
"train_samples_per_second": 5.95,
|
| 10 |
+
"train_steps_per_second": 0.744
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 88.31598864711448,
|
| 4 |
+
"eval_f1": 94.44474801701165,
|
| 5 |
+
"eval_samples": 10808
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.6275850592107118,
|
| 4 |
+
"train_runtime": 29795.4441,
|
| 5 |
+
"train_samples": 88638,
|
| 6 |
+
"train_samples_per_second": 5.95,
|
| 7 |
+
"train_steps_per_second": 0.744
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 22160,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 2.9323104693140794e-05,
|
| 13 |
+
"loss": 1.365,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 2.864620938628159e-05,
|
| 19 |
+
"loss": 0.9493,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"learning_rate": 2.7969314079422385e-05,
|
| 25 |
+
"loss": 0.8795,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 2.729241877256318e-05,
|
| 31 |
+
"loss": 0.8473,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.23,
|
| 36 |
+
"learning_rate": 2.6615523465703972e-05,
|
| 37 |
+
"loss": 0.8401,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 2.5938628158844765e-05,
|
| 43 |
+
"loss": 0.8402,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"learning_rate": 2.526173285198556e-05,
|
| 49 |
+
"loss": 0.8296,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 2.4584837545126353e-05,
|
| 55 |
+
"loss": 0.7466,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.41,
|
| 60 |
+
"learning_rate": 2.390794223826715e-05,
|
| 61 |
+
"loss": 0.7833,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.45,
|
| 66 |
+
"learning_rate": 2.3231046931407943e-05,
|
| 67 |
+
"loss": 0.8053,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.5,
|
| 72 |
+
"learning_rate": 2.2554151624548737e-05,
|
| 73 |
+
"loss": 0.7537,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.54,
|
| 78 |
+
"learning_rate": 2.1877256317689534e-05,
|
| 79 |
+
"loss": 0.7497,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.59,
|
| 84 |
+
"learning_rate": 2.1200361010830327e-05,
|
| 85 |
+
"loss": 0.7674,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.63,
|
| 90 |
+
"learning_rate": 2.0523465703971117e-05,
|
| 91 |
+
"loss": 0.7417,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.68,
|
| 96 |
+
"learning_rate": 1.9846570397111914e-05,
|
| 97 |
+
"loss": 0.7584,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.72,
|
| 102 |
+
"learning_rate": 1.9169675090252708e-05,
|
| 103 |
+
"loss": 0.7545,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.77,
|
| 108 |
+
"learning_rate": 1.84927797833935e-05,
|
| 109 |
+
"loss": 0.766,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.81,
|
| 114 |
+
"learning_rate": 1.7815884476534298e-05,
|
| 115 |
+
"loss": 0.7339,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.86,
|
| 120 |
+
"learning_rate": 1.7138989169675092e-05,
|
| 121 |
+
"loss": 0.714,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9,
|
| 126 |
+
"learning_rate": 1.6462093862815885e-05,
|
| 127 |
+
"loss": 0.7173,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.95,
|
| 132 |
+
"learning_rate": 1.578519855595668e-05,
|
| 133 |
+
"loss": 0.7207,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.99,
|
| 138 |
+
"learning_rate": 1.5108303249097474e-05,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0,
|
| 144 |
+
"eval_exact_match": 88.30652790917692,
|
| 145 |
+
"eval_f1": 94.12994072622395,
|
| 146 |
+
"step": 11080
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.04,
|
| 150 |
+
"learning_rate": 1.4431407942238268e-05,
|
| 151 |
+
"loss": 0.5424,
|
| 152 |
+
"step": 11500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.08,
|
| 156 |
+
"learning_rate": 1.3754512635379063e-05,
|
| 157 |
+
"loss": 0.4775,
|
| 158 |
+
"step": 12000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.13,
|
| 162 |
+
"learning_rate": 1.3077617328519855e-05,
|
| 163 |
+
"loss": 0.483,
|
| 164 |
+
"step": 12500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.17,
|
| 168 |
+
"learning_rate": 1.240072202166065e-05,
|
| 169 |
+
"loss": 0.4584,
|
| 170 |
+
"step": 13000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.22,
|
| 174 |
+
"learning_rate": 1.1723826714801445e-05,
|
| 175 |
+
"loss": 0.4604,
|
| 176 |
+
"step": 13500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.26,
|
| 180 |
+
"learning_rate": 1.1046931407942239e-05,
|
| 181 |
+
"loss": 0.4531,
|
| 182 |
+
"step": 14000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.31,
|
| 186 |
+
"learning_rate": 1.0370036101083034e-05,
|
| 187 |
+
"loss": 0.4533,
|
| 188 |
+
"step": 14500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.35,
|
| 192 |
+
"learning_rate": 9.693140794223826e-06,
|
| 193 |
+
"loss": 0.4583,
|
| 194 |
+
"step": 15000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.4,
|
| 198 |
+
"learning_rate": 9.016245487364621e-06,
|
| 199 |
+
"loss": 0.4623,
|
| 200 |
+
"step": 15500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.44,
|
| 204 |
+
"learning_rate": 8.339350180505416e-06,
|
| 205 |
+
"loss": 0.4756,
|
| 206 |
+
"step": 16000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.49,
|
| 210 |
+
"learning_rate": 7.66245487364621e-06,
|
| 211 |
+
"loss": 0.4339,
|
| 212 |
+
"step": 16500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.53,
|
| 216 |
+
"learning_rate": 6.985559566787004e-06,
|
| 217 |
+
"loss": 0.4502,
|
| 218 |
+
"step": 17000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.58,
|
| 222 |
+
"learning_rate": 6.308664259927798e-06,
|
| 223 |
+
"loss": 0.44,
|
| 224 |
+
"step": 17500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.62,
|
| 228 |
+
"learning_rate": 5.631768953068592e-06,
|
| 229 |
+
"loss": 0.4057,
|
| 230 |
+
"step": 18000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.67,
|
| 234 |
+
"learning_rate": 4.954873646209386e-06,
|
| 235 |
+
"loss": 0.4528,
|
| 236 |
+
"step": 18500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.71,
|
| 240 |
+
"learning_rate": 4.277978339350181e-06,
|
| 241 |
+
"loss": 0.4447,
|
| 242 |
+
"step": 19000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.76,
|
| 246 |
+
"learning_rate": 3.6010830324909746e-06,
|
| 247 |
+
"loss": 0.4338,
|
| 248 |
+
"step": 19500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.81,
|
| 252 |
+
"learning_rate": 2.924187725631769e-06,
|
| 253 |
+
"loss": 0.4449,
|
| 254 |
+
"step": 20000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.85,
|
| 258 |
+
"learning_rate": 2.247292418772563e-06,
|
| 259 |
+
"loss": 0.4263,
|
| 260 |
+
"step": 20500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.9,
|
| 264 |
+
"learning_rate": 1.5703971119133576e-06,
|
| 265 |
+
"loss": 0.4382,
|
| 266 |
+
"step": 21000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.94,
|
| 270 |
+
"learning_rate": 8.935018050541516e-07,
|
| 271 |
+
"loss": 0.397,
|
| 272 |
+
"step": 21500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.99,
|
| 276 |
+
"learning_rate": 2.1660649819494586e-07,
|
| 277 |
+
"loss": 0.435,
|
| 278 |
+
"step": 22000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.0,
|
| 282 |
+
"eval_exact_match": 88.31598864711448,
|
| 283 |
+
"eval_f1": 94.44474801701165,
|
| 284 |
+
"step": 22160
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.0,
|
| 288 |
+
"step": 22160,
|
| 289 |
+
"total_flos": 8.247163627136614e+16,
|
| 290 |
+
"train_loss": 0.6275850592107118,
|
| 291 |
+
"train_runtime": 29795.4441,
|
| 292 |
+
"train_samples_per_second": 5.95,
|
| 293 |
+
"train_steps_per_second": 0.744
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"max_steps": 22160,
|
| 297 |
+
"num_train_epochs": 2,
|
| 298 |
+
"total_flos": 8.247163627136614e+16,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": null
|
| 301 |
+
}
|